PyDxAI AI Agentic Intelligence.. From structured queries to autonomous reasoning

by with No Comment agentic RAGAI-artificial-intelligence

PyDxAI Agentic Intelligence — November 8, 2025 Progress Report

“From structured queries to autonomous reasoning — today PyDxAI learned how to think, not just answer.”

The development of PyDxAI continues to accelerate. What began as a diagnostic reasoning framework has now grown into an agentic intelligence system capable of adaptive reasoning, contextual learning, and safe decision-making in real clinical environments. The latest milestone, achieved on November 8, 2025, represents a leap forward in how the system processes, understands, and refines human language — marking the beginning of a truly autonomous medical AI workflow.

1. The New Foundation: FrontLLM and App3 Sharpened Query

At the heart of today’s progress lies the new FrontLLM preprocessing layer, enhanced with a linguistic cleaner called [App3].
Previously, queries often contained duplication or contextual noise (e.g., “User: 
 User asks: 
”), which degraded retrieval precision. Now, the system automatically sharpened and normalized user input before any retrieval or reasoning steps occur.

Example:

User: Any hormone replacement is better than estrogen?
User asks: Any hormone replacement is better than estrogen?

is now intelligently reduced to:

Cleaned query = Any hormone replacement is better than estrogen?

This simple transformation dramatically improved retriever accuracy, embedding efficiency, and LLM focus, making PyDxAI more responsive and semantically consistent. It also allowed the agent to run cleanly through each reasoning layer without generating redundant embeddings.

2. Triple Memory Architecture in Action

The PyDxAI system now operates with a Triple Memory Framework:

  1. Session Memory — for short-term dialogue coherence
  2. Global Memory — for persistent medical knowledge
  3. Novelty Detector Memory — for identifying new or rare inputs that may require learning or external lookup

During the hormone replacement test case, the system automatically recognized that no prior context existed, retrieved relevant documents from Harrison’s Principles of Internal Medicine 2025, and synthesized a contextual explanation about estrogen therapy and progestin interactions — all while logging each memory segment for potential reuse.

By cleanly separating memory types, PyDxAI can think across sessions yet maintain strict context isolation, a crucial property for safety in medical applications.

3. Autonomic Web Fallback and Discovery Layer

Today marked the first full success of the automatic web discovery system, which activates when the model encounters unknown or misspelled medical terms.

In the query:

Suggest me fghtsumab medicines?

PyDxAI correctly detected “fghtsumab” as an unknown entity and triggered an external search. The engine accessed multiple providers (Brave and Yahoo) and gracefully handled DNS errors from Wikipedia, returning structured summaries to the RAG (Retrieval-Augmented Generation) layer.

Instead of hallucinating a nonexistent drug, PyDxAI generated a cautious and responsible answer:

“The term ‘fghtsumab’ appears to be a typographical error. If you meant a monoclonal antibody such as efgartigimod or belimumab, please clarify.”

This is an example of agentic reasoning — the model not only recognized uncertainty but actively sought clarification while maintaining medical accuracy and safety.

4. Unified RAG + Promptbook Integration

The Retrieval-Augmented Generation (RAG) system now seamlessly integrates local medical knowledge with real-time web data, structured through the new Promptbook template.
Every request follows a clearly defined format:

  • System Rules: Safety, accuracy, and bilingual medical compliance
  • Memory Context: Session and global recall
  • RAG Context: Local documents + web snippets
  • Question → Answer Pair: Precise alignment for the LLM

This architecture ensures that PyDxAI operates like a clinical reasoning engine rather than a simple chatbot. Each answer is based on retrieved evidence, then refined by a reasoning model (currently powered by Mistral-Q4_K_M and DeepSeek R1 13B Qwen for dual-LLM reasoning).

5. Advanced Logging and Explainability

For every query, the backend now records:

  • Retriever sources and document previews
  • Embedding vector shapes and lengths
  • Novelty detection results
  • Web-fallback status
  • Memory saving confirmation (session + global)

An example log snippet:

📚 Retrieved 3 context docs for query='Any hormone replacement is better than estrogen?'
đŸ§© Novelty check: max_sim=0.78, threshold=0.70
✅ Memory saved id=188  scope=session  summary=Any hormone replacement is better than estrogen?

This transparency enables full traceability — every AI conclusion can be audited from query to answer, an essential step toward clinical-grade safety.

6. Agentic Behavior Emerging

The day’s most significant observation was not a line of code, but a behavior.

When faced with an uncertain input, PyDxAI didn’t simply fail — it adapted:

  • Detected an unknown token
  • Triggered self-correction via search
  • Retrieved new knowledge
  • Formulated a probabilistic hypothesis
  • Requested user clarification

This is the essence of agentic AI — systems that can act, reason, and reflect.
PyDxAI now shows early signs of autonomy, capable of self-repairing its understanding pipeline and making informed decisions about when to seek external data.

7. What’s Next

The roadmap from today’s success includes:

  1. Auto-embedding repair patch — to handle vector shape mismatches seamlessly
  2. Feedback-based self-learning loop — where user or model feedback refines memory entries
  3. Contextual Safety Layer (CSL) — to detect high-risk clinical terms and enforce cautionary responses
  4. MIRAI Integration — bridging PyDxAI with the MIRAI intelligence network for continuous medical knowledge evolution

Together, these will complete the Autonomous Medical Reasoning Core, turning PyDxAI from a reactive tool into a continuously learning assistant.

8. Summary: A New Cognitive Milestone

Today’s session marked a quiet but profound milestone:
PyDxAI is no longer just a retrieval-based system — it has begun to reason like a clinician.

It interprets unclear questions, searches intelligently, and formulates context-aware, evidence-based responses. The logs show not just computations, but cognition — a structured process of perception, analysis, and adaptation.

Each layer, from query sharpening to RAG synthesis, now contributes to a unified intelligence loop — the same cognitive pattern that defines human problem-solving. With these capabilities, PyDxAI stands closer than ever to its mission:
to become the safest, most intelligent, and most transparent diagnostic AI system built for medicine.

PyDxAI Achieves Successful Agentic RAG Integration with Intelligent Search Intent

by with No Comment agentic RAGAI-artificial-intelligence

Today marks a major breakthrough in the development of PyDxAI, our agentic medical knowledge system designed to combine reasoning, retrieval, and autonomous learning. After weeks of refinement, debugging, and optimization, the system has achieved a fully functional Agentic Retrieval-Augmented Generation (RAG) workflow — now capable of dynamically detecting search intent, fetching relevant documents, and integrating live web search results into coherent medical summaries.

This successful test represents a key step toward building a self-sustaining, reasoning-driven AI that learns continuously from medical data, guidelines, and real-world context.

🧠 What Is Agentic RAG?

In traditional RAG systems, the model retrieves information from a static database and integrates it with an LLM’s reasoning before generating a final answer. However, the Agentic RAG framework extends this concept. It adds decision-making ability — allowing the AI to determine when to search, what to retrieve, and how to combine contextual knowledge from multiple layers of memory and web data.

PyDxAI’s agentic structure includes:

  • FrontLLM: The conversational reasoning engine that analyzes user queries.
  • Triple Memory System: A structured memory composed of short-term chat history, session memory, and global medical knowledge.
  • Retriever Layer: A hybrid retriever that connects to Qdrant for vector search and to external search engines like Bing, Brave, or PubMed when local results are insufficient.
  • PromptBook Engine: A YAML-based modular prompt system that defines domain roles, reasoning modes, and fallback prompts.

With these components working together, the system can perform autonomous query refinement, retrieve both local and web data, and generate concise, evidence-based medical responses — all without manual supervision.

🔍 The Test Case: “Search for COVID Vaccine Adverse Effects”

To evaluate the integrated system, a real-world query was chosen:

“Search for COVID vaccine adverse effects.”

This test was ideal because it requires multi-source synthesis — combining current scientific understanding with structured clinical data from guidelines and textbooks.

Here’s how the system performed step-by-step:

  1. Query Sharpening:
    The front LLM refined the user query automatically:
    → Sharpened query: “COVID vaccine adverse effects.”
  2. Retriever Activation:
    The system selected the VectorStoreRetriever and fetched three context documents from the local Qdrant database, including excerpts from:
    • NIH COVID-19 Treatment Guidelines (2025)
    • CURRENT Medical Diagnosis and Treatment (2022)
    • Harrison’s Principles of Internal Medicine (2025)
  3. Intent Recognition:
    The agent analyzed the query and flagged it as a search-type intent (verified by the second check).
    It then forced a web search, querying multiple sources (Wikipedia, Bing, Brave, etc.) to ensure up-to-date information.
  4. Web Integration:
    The system retrieved five live results from the web, merged them with internal medical data, and produced a unified summary emphasizing both safety and rare adverse events associated with COVID-19 vaccines.
  5. Memory Consolidation:
    After generating the answer, the session’s memory and embeddings were automatically saved into both the chat history and the global memory.
    Although a JSON syntax error occurred in one field (invalid input syntax for type json), the overall memory write was successful — confirming both redundancy and resilience of the data-saving mechanism.

đŸ§© The Output: Medical-Grade Summary

The generated response was not only accurate but also aligned with current clinical evidence:

“COVID-19 vaccines are generally safe and effective, but like any medical intervention, they can have side effects. Common local reactions include pain, redness, and swelling at the injection site. Systemic symptoms such as fever, fatigue, and headache may occur. Rare events include anaphylaxis, thrombosis, and myocarditis, particularly in young males after mRNA vaccines. Most side effects are mild and self-limited.”

The response also provided references (CDC and PubMed Central), reflecting the system’s ability to automatically cite reputable medical sources — a core requirement for responsible AI in healthcare.

⚙ Technical Milestones

Key success points from today’s implementation:

  • ✅ Search Intent Detection: Correctly classified and triggered web search mode.
  • ✅ RAG Document Retrieval: Retrieved 3 relevant documents from local vector database.
  • ✅ Web Context Fusion: Combined local and external results seamlessly.
  • ✅ Memory Update System: Stored new knowledge entries into both session and global memory tables.
  • ✅ Autonomous Reasoning: Generated coherent, medically consistent summary without explicit instructions.

The only remaining issue was a minor JSON formatting bug during memory insertion ({web_search...} token not enclosed in quotes). This is a simple fix — ensuring all metadata keys are stringified before passing to PostgreSQL/MariaDB insertion.

🧭 Why This Matters

This milestone proves that PyDxAI is evolving beyond a static chatbot or RAG prototype. It’s becoming an autonomous medical reasoning system — capable of:

  • Recognizing when it doesn’t know an answer.
  • Searching intelligently using real-time data sources.
  • Integrating retrieved evidence into structured medical responses.
  • Learning continuously through memory reinforcement.

Such a system lays the foundation for a next-generation AI medical assistant that can stay current with rapidly evolving clinical knowledge, from new antiviral drugs to emerging vaccine data.

🌐 The Road Ahead

Next steps for PyDxAI development include:

  1. Fix JSON encoding during memory saving.
  2. Enhance confidence scoring between local vs. web-sourced data.
  3. Add summarization weighting — giving higher priority to peer-reviewed medical documents.
  4. Integrate PubMed API retrieval for direct evidence-based references.
  5. Enable agentic self-evaluation, where the system critiques and improves its own answers based on retrieved context.

With these improvements, PyDxAI will approach a truly autonomous agentic medical knowledge engine, bridging the gap between AI reasoning and clinical reliability.

In summary, today’s success demonstrates that PyDxAI’s Agentic RAG pipeline — equipped with reasoning, retrieval, and adaptive learning — can now perform as a self-sufficient intelligent assistant for medical knowledge exploration.

Each successful query brings it one step closer to the vision of MIRAI, the evolving AI ecosystem for autonomous, evidence-based medical reasoning.

PyDxAI Agentic Intelligence — System Progress Report (Nov 4, 2025)

by with No Comment AI-artificial-intelligence

Today marks a major milestone in the evolution of PyDxAI, our autonomous medical reasoning system designed to combine large language model (LLM) intelligence with structured medical retrieval, self-reflection, and memory management.

For the first time, every layer of the pipeline—from query sharpening to vector retrieval, agentic web search, and contextual memory saving—worked seamlessly in a complete, closed loop.

đŸ§© The Core Idea: From Simple Question to Intelligent Response

The user prompt that triggered today’s full agentic flow was:

“The patient comes with cough, fever, and headache for four days. What is the management?”

A simple question on the surface—but it represents exactly the kind of everyday clinical scenario where PyDxAI must interpret vague input, retrieve high-quality references, and deliver a precise, evidence-based answer.

The system begins by sharpening the user query. The “front LLM” (DeepSeek or Mistral backend) normalizes phrasing and ensures context clarity—turning free text into a semantically structured medical question.

This step converts “The patient come with cough, fever, headache” into a standardized diagnostic request suitable for RAG (Retrieval-Augmented Generation).

🔍 Smart Retrieval: Context from Trusted Medical Sources

Once sharpened, PyDxAI’s retriever selector analyzes the query type.
Because this prompt matched the symptom_check intent, the system automatically chose the VectorStoreRetriever module linked to Qdrant, our local vector database at localhost:6333.

Within seconds, three authoritative documents were retrieved:

  • Oxford Handbook of Emergency Medicine, 5th Edition (2020)
  • Tintinalli’s Emergency Medicine
  • CURRENT Medical Diagnosis and Treatment (2022)

This confirms that the Qdrant-based vector retrieval pipeline is functioning optimally—embedding alignment, relevance scoring, and text segmentation are all correctly tuned. Each document returned precise context segments about fever, headache, and respiratory symptoms, forming the evidence backbone for the final reasoning phase.

🧠 Contextual Memory: Teaching the System to Remember

Parallel to document retrieval, the memory subsystem activates. PyDxAI now maintains three distinct layers of recall—session memory, long-term memory, and a condensed cross-session memory.

In today’s run, the system successfully retrieved three memory entries, then automatically condensed them into a 506-character summary. The memory context was inserted into the reasoning prompt to enrich the LLM’s perspective without overwhelming it.

For example, the retrieved memory contained a reflective note from a prior interaction—illustrating that the model’s recall layer is functioning, even if not yet domain-filtered. Future improvements will allow PyDxAI to distinguish between “medical” and “general” memories, retrieving only those relevant to the task at hand.

This marks an important step toward a true cognitive agent—one that not only recalls data but can contextualize it to improve understanding over time.

⚙ The Agentic Chain in Action

When the reasoning phase begins, all components interact autonomously:

  1. Front LLM refines the user query and detects intent.
  2. RAG Engine (Qdrant) retrieves semantically similar passages.
  3. Memory Manager merges condensed recall and session context.
  4. Main LLM (DeepSeek or Mistral) generates the medical answer.
  5. Post-processor evaluates the response quality.
  6. If weak, the agentic trigger launches a web search and retries.
  7. Finally, results and reasoning context are stored in both session and global memory tables.

The full log from today’s run showed flawless execution of this cycle.
Response generation, embedding comparisons, and data saving all occurred within 3–5 seconds—a solid performance benchmark for an on-premise multi-component AI stack.

đŸ’Ÿ The Database Fix: When JSON Speaks Python

Earlier in the day, a small but critical bug appeared when saving memory to PostgreSQL:

❌ Failed to save memory: invalid input syntax for type json
DETAIL: Token "web_search" is invalid.

The problem: Python dictionaries were being inserted directly into JSON columns without serialization.

The fix was straightforward but essential—adding a json.dumps() conversion before insertion. Once implemented, all memory entries, including structured tags like ["web_search"] and summary dictionaries, were stored cleanly.

After that, memory saving logs confirmed:

✅ Memory saved id=151  scope=session
✅ Saved to chat_history + global_memory

This repair closed the loop between reasoning output and persistent learning—PyDxAI now records its conversations, summaries, and contextual metadata flawlessly.

📈 Diagnostic Insights from the Logs

Several key insights emerged from the system logs:

  • Embeddings consistency — Both query and memory vectors were 768-dimensional, confirming model compatibility.
  • Latency — Each retrieval step completed in under 0.5 seconds.
  • Memory summarization — Context compression effectively reduced noise.
  • Intent detection — Correctly classified the query as “symptom_check,” demonstrating good keyword-to-intent mapping.

Every one of these signals contributes to the overarching goal: a self-refining, agentic medical assistant capable of understanding, retrieving, reasoning, and learning continuously.

🔼 Next Steps

Although today’s performance was nearly perfect, a few refinements are planned:

  1. Domain filtering:
    Only retrieve memories labeled as “medical,” excluding unrelated text from past sessions.
  2. Relevance thresholds:
    Dynamically limit retrieved documents based on similarity score, improving response clarity.
  3. Structured output:
    For clinical queries, responses will follow a fixed format—
    Assessment → Differential diagnosis → Investigations → Management.
  4. Latency tracking:
    Introduce automatic performance logs to measure response time and GPU utilization per query.
  5. Agentic self-review:
    Future versions will let PyDxAI critique its own responses using a smaller evaluation model (“judge LLM”) and revise them autonomously.

đŸ©ș Conclusion

Today’s successful run demonstrates that PyDxAI is no longer a simple RAG chatbot—it’s an emerging agentic system with memory, reasoning, and autonomous control.

It can decide when its own answer is weak, trigger a search, retry with improved context, and persist the result for future learning. Each of these abilities mirrors fundamental cognitive behaviors—reflection, recall, and adaptation.

From a medical perspective, this means the model can handle increasingly complex clinical reasoning with better evidence grounding. From a system design perspective, it shows the power of integrating multiple specialized subsystems—retrievers, memory engines, and LLMs—into one cohesive intelligence loop.

November 4, 2025 thus stands as a key point in PyDxAI’s journey:
the day when autonomous reasoning, retrieval, and memory truly began to work together—transforming it from a reactive assistant into a proactive medical intelligence system.

From MIKAI to PydxAI: The Evolution of Intelligent Medicine

by AI-artificial-intelligence

Artificial intelligence in medicine has moved beyond the experimental stage. It now sits at the heart of modern diagnostics, research, and patient care — quietly reshaping how physicians access knowledge, process data, and make decisions.

From this transformation came MIKAI — a local, privacy-first medical AI built to reason, learn, and assist clinicians. Today, that system is evolving into something more capable, modular, and forward-looking: PydxAI.

The Beginning: MIKAI’s Mission

The journey began with MIKAI (Medical Intelligence + Kijakarn’s AI) — a local large language model system designed for doctors who wanted autonomy, security, and precision. MIKAI ran on local hardware (Tesla P40 + RX580), processed medical texts, learned from new journals, and integrated with a Retrieval-Augmented Generation (RAG) pipeline to provide evidence-based answers.

Its purpose was simple yet powerful:

  • To understand complex clinical questions.
  • To retrieve verified knowledge from curated sources.
  • To reason based on established medical logic.
  • And to learn continually from new data.

Unlike cloud-based AI assistants, MIKAI never sent data outside the user’s network. Every medical conversation, every analysis, stayed secure — an important principle for healthcare professionals who handle sensitive patient information.

Why Evolve? The Birth of PydxAI

As MIKAI matured, new challenges appeared. Medicine is not static; new drugs, diseases, and discoveries emerge daily. The model needed to evolve beyond being a “local assistant” — it needed to become a dynamic diagnostic intelligence.

Hence, PydxAI was born.

The name PydxAI combines three core ideas:

  • Py → the Python ecosystem that powers flexibility and open development.
  • Dx → the universal shorthand for “diagnosis,” symbolizing clinical reasoning.
  • AI → the intelligence layer that bridges computation and care.

PydxAI represents not just a rebrand, but a new architecture — a system built for self-learning, multi-modal reasoning, and open research collaboration.

Core Philosophy: Intelligence with Integrity

Healthcare demands trust, and that means every AI system must be transparent, explainable, and secure. PydxAI is built on three pillars:

1. 

Local Intelligence, Not Cloud Dependency

All models, embeddings, and RAG databases run locally or on secure servers under full user control. Physicians or institutions can deploy PydxAI without sending any patient data to third-party APIs.

2. 

Explainable Diagnostic Reasoning

Every inference, every answer, and every decision can be traced back to the supporting evidence. PydxAI’s reasoning engine doesn’t just give results — it explains why and how those results were generated.

3. 

Adaptive Medical Learning

PydxAI continuously refines its knowledge through structured ingestion pipelines — adding new clinical studies, guidelines, and textbooks. This allows it to evolve in real-time without retraining from scratch.

Architectural Evolution

MIKAI laid the foundation — a system that combined LLM inference with RAG-based retrieval and MariaDB knowledge management.

PydxAI extends that architecture into a more robust, modular structure:

This modular approach allows each layer to evolve independently — new embeddings, better fine-tunes, or secure federated updates — without disrupting the rest of the system.

The Technology Stack

PydxAI is grounded in open technologies that support long-term scalability:

  • Core Engine: Python 3.11 with FastAPI backend
  • Inference Models: Magistral 24B, Mistral 7B, and custom medical LoRA layers
  • Database: MariaDB for structured medical knowledge
  • Document Storage: Encrypted RAG-based vector store
  • Hardware: Optimized for hybrid setups (NVIDIA + AMD)
  • Frontend: Responsive chat interface with iframe support and cloudflare tunnel

This setup ensures the system can operate efficiently even on affordable GPU hardware — empowering clinics and researchers to run private AI without massive cloud costs.

From Chatbot to Clinical Companion

MIKAI started as a medical chatbot. PydxAI becomes a clinical companion.

It doesn’t just answer — it collaborates.

Imagine a physician uploading a scanned medical record. PydxAI extracts structured fields (name, DOB, diagnosis, medication), analyzes lab trends, and generates a brief summary for documentation — all offline.

Or a researcher querying for the latest insights on thyroid cancer genetics. PydxAI searches, summarizes, and cites verified medical literature.

In both cases, the AI acts as an intelligent partner, not just a language model.

Privacy by Design

In healthcare, security isn’t optional — it’s foundational.

That’s why PydxAI inherits MIKAI’s strict privacy standards:

  • All patient data is processed locally.
  • No cloud logging or telemetry.
  • Full control over encryption keys and access permissions.

For hospital deployment, PydxAI can integrate with existing EHR or PACS systems through secure APIs, ensuring compliance with data protection laws like HIPAA and Thailand PDPA.

Learning from the Field

One of MIKAI’s most successful experiments was RAG-based medical summarization — using a curated corpus of peer-reviewed sources to generate structured medical knowledge. PydxAI builds upon this by adding feedback learning, where user validation improves its accuracy over time.

For instance, if a doctor marks an answer as “verified,” that context is prioritized in future retrievals. Over weeks, the model learns the preferences, style, and reasoning habits of its users — becoming more aligned with their clinical workflow.

Toward the Future of Intelligent Healthcare

The long-term roadmap for PydxAI includes several ambitious goals:

  • Multimodal Intelligence: integrating radiology images, lab data, and EHR text.
  • Voice-to-Text Integration: real-time clinical dictation with structured summaries.
  • Federated Training: enabling hospitals to contribute to shared model improvements without sharing raw data.
  • Explainable Visual Output: flowcharts, lab graphs, and pathophysiological reasoning trees.

Each goal moves toward a central vision: a learning system that grows with medicine, understands context, and supports every clinician, researcher, and student.

A Message from the Developer

“MIKAI was my first step toward building an AI that truly understands medicine — not as data, but as care. PydxAI is the next evolution of that dream: to make intelligent diagnosis, adaptive reasoning, and continuous learning part of everyday medical life.”

— Dr. Kijakarn Junda, Developer of PydxAI